© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 58255
    Prev
    Next
    INDEX
    Explanations

    as expected or intended

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/olmo-3-saes/olmo-3-1025-7b
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ansa
    -0.08
    enga
    -0.08
     dictated
    -0.07
     theirs
    -0.07
     bott
    -0.07
     Paginator
    -0.07
     inconsistency
    -0.07
    ovich
    -0.07
     NOW
    -0.07
     appropriate
    -0.07
    POSITIVE LOGITS
     prior
    0.10
     pref
    0.10
    HD
    0.10
     compos
    0.09
     ide
    0.09
     predictions
    0.09
     lifestyle
    0.09
     Bridges
    0.09
    coma
    0.08
     discussion
    0.08
    Activations Density 0.070%

    No Known Activations